Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    referring to a group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     своей
    0.50
     Provides
    0.48
     provides
    0.46
     alone
    0.45
     conforms
    0.45
     requires
    0.44
     svojim
    0.44
     providing
    0.43
     Conform
    0.42
     Provide
    0.42
    POSITIVE LOGITS
    స్తారు
    0.56
     хотят
    0.54
     quieren
    0.54
     vogliono
    0.52
     mettent
    0.50
     querem
    0.48
    ették
    0.47
     தெரிவித்தனர்
    0.46
     делают
    0.46
     решили
    0.46
    Act Density 0.017%

    No Known Activations